2799 Model Context Protocol servers — searchable, rated, ready to install.
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
NOAA STOFS storm surge forecasts, observation validation, and OPeNDAP data
Token guard and rate limiter preventing runaway API cost spikes for OpenAI and Anthropic.
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
Repairs malformed JSON from LLM output, validated against a schema. Paid per call via Stripe.
Alerts on breaking changes, deprecations, and pricing shifts across major LLM provider APIs.
Draft, check and schedule posts to your social accounts from Claude, ChatGPT, Cursor or VS Code.
RuleStack: Search real AGENTS.md, CLAUDE.md and Cursor rules files.
GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations
Lints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI d
Catches leaked credentials and PII in outbound LLM prompts
Flashcards for Claude: create, edit and study StudyCards decks with FSRS spaced repetition.
Make AI-drawn video from chat: your LLM draws every frame in code; add narration, music and SFX.
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Etsy search + Etsy shop sales: live listing rows and sales counters via Apify MCP.
Publish apps from Claude Code, Codex or Cursor to your team, behind sign-in, with a database.
See whether ChatGPT, Claude and Gemini recommend a startup's product, and who they name instead.
Schedule, check and retry social posts from Claude or ChatGPT; going live waits for a tap.
Create private AI images with your UlazAI account: pick a model, confirm, generate, download.
Create, launch, and manage Meta + Google ads from Claude and ChatGPT.
Web pages and whole sites to clean Markdown for RAG and AI agents. Crawls links and sitemaps.
GOES-18/19 satellite imagery — visible, infrared, water vapor, and composites via NOAA
Recherche de téléfilms de Noël et de leurs diffusions TV, en lecture seule, horaires Europe/Paris.
AI Model Experiments MCP ('Model Lab') — run the same prompts across many
POST /mcp